Age | Commit message (Collapse) | Author | Files | Lines |
|
Better clean that up before some automation starts to complain about it
Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Implement functions to do the RAS error injection and
query EDC counter.
Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
1. Add IP prefix for the IP related codes.
2. Refactor the code to clear EDC counter.
Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
To avoid calling RAS related functions when RAS feature isn't
supported in hardware. Change to check supported features, instead
of checking asic type.
v2: reuse amdgpu_ras_is_supported function, instead of introducing
a new flag for hardware ras feature.
Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Reading CP_MEM_SLP_CNTL register with RREG32_SOC15 macro will lead to
hang when GPU is in "gfxoff" state.
I do a uniform substitution here.
Signed-off-by: chen gong <curry.gong@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
register by KIQ
Move amdgpu_virt_kiq_rreg/amdgpu_virt_kiq_wreg function to amdgpu_gfx.c,
and rename them to amdgpu_kiq_rreg/amdgpu_kiq_wreg.Make it generic and
flexible.
Signed-off-by: chen gong <curry.gong@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
[Why]
PM4 packet size for flush message was oversized.
[How]
Packet size adjusted to allocate flush + fence packets.
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
The mec ucode will set the CP_HQD_ACTIVE bit while the queue is mapped by
MAP_QUEUES packet. So we only need set cp active field for kiq queue.
Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
[Why]
There are HW-indpendent functions that enables and disables kcq. These functions use
the kiq_pm4_funcs implementation.
[How]
Local kcq enable and disable functions removed and replace it by the generic kcq
enable under amdgpu_gfx
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
tlbs invalidate pointer function added to kiq_pm4_funcs struct.
This way, tlb flush can be done through kiq member.
TLBs invalidatation implemented for gfx9 and gfx10.
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Functions implemented from kiq_pm4_funcs struct members
for gfx_v9 version.
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
On Arcturus, data fabric hashing is set by the VBIOS, and
affects which addresses map to which memory channels. The
gfx core's caches also need to know this mapping, but the
hash settings for these these caches is set by the driver.
This change queries the DF to understand how the VBIOS
configured DF, then matches the TC hash configuration bits
to do the same thing.
v2: squash in warning fix
Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
All of the sdma stuff these were used for moves to
the sdma code, so remove them.
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
SDMA edc counter registers were added in gfx edc counters
array. When querying gfx error counter in that array, there
is no way to differentiate sdma instance number for different
asic and then results to NULL pointer access when trying to
read sdma register base address for instances greater
than 2 on Vega20.
In addition, this also results to wrong gfx error counters
since it actually added sdma edc counters.
Therefore, sdma edc counter registers should be separated
from gfx edc counter regsiter array and only get initialized
when driver tries to enable sdma ras.
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Put it on one line to avoid whitespace issues when
printing in the log.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Add mmSDMA2-7_EDC_COUNTER to support Arcturus
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Add mmCOMPUTE_STATIC_THREAD_MGMT_SE4-7 to support Arcturus
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Replace ARRAY_SIZE with size variables to support
different ASICs.
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
When smu version is larger than 0x41e2b, it will load
raven_kicker_rlc.bin.To enable gfxoff for raven_kicker_rlc.bin,it
needs to avoid adev->pm.pp_feature &= ~PP_GFXOFF_MASK when it loads
raven_kicker_rlc.bin.
Signed-off-by: changzhu <Changfeng.Zhu@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
SPI limits total CS waves in flight per SE to no more than 32 * num_cu and
we need to stuff 40 waves on a CU to completely clean the SGPR. This is
accomplished in the WR by cleaning the SE in two steps, half of the CU per
step.
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Yong Zhao <Yong.Zhao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
issue:
kernel would report a warning from a double unpin
during the driver unloading on the CSB bo
why:
we unpin it during hw_fini, and there will be another
unpin in sw_fini on CSB bo.
fix:
actually we don't need to pin/unpin it during
hw_init/fini since it is created with kernel pinned,
we only need to fullfill the CSB again during hw_init
to prevent CSB/VRAM lost after S3
v2:
get_csb in init_rlc so hw_init() will make CSIB content
back even after reset or s3
v3:
use bo_create_kernel instead of bo_create_reserved for CSB
otherwise the bo_free_kernel() on CSB is not aligned and
would lead to its internal reserve pending there forever
take care of gfx7/8 as well
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
For Arcturus, increase dispatch packet number to stress scheduler.
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Clear SDMA and HDP EDC counter in GPR workarounds.
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
gfx memory should be initialized before enabling
DED and FUE field in mmGB_EDC_MODE
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
The struct soc15_ras_field_entry will be reused by
other IPs, such as mmhub and gc
v2: rename ras_subblock_regs to gc_ras_fields_vg20,
because the future asic maybe have a different table.
Signed-off-by: Dennis Li <dennis.li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
There are still combinations of sbios and firmware that
are not stable.
Bug: https://bugzilla.kernel.org/show_bug.cgi?id=204689
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
It will cause modprobe atombios stuck problem in raven2 if it doesn't
allow direct upload save restore list from gfx driver.
So it needs to allow direct upload save restore list for raven2
temporarily.
Signed-off-by: changzhu <Changfeng.Zhu@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
To properly handle the option parsing ordering.
Reviewed-by: Yong Zhao <yong.zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Using unified VBIOS has performance drop in sriov environment.
The fix is switching to another register instead.
Signed-off-by: Eric Huang <JinhuiEric.Huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
It needs to add warning to update firmware in gfx9
in case that firmware is too old to have function to
realize dummy read in cp firmware.
Signed-off-by: changzhu <Changfeng.Zhu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Direct uploading save/restore list via mmio register writes breaks the security
policy. Instead, the driver should pass s&r list to psp.
For all the ASICs that use rlc v2_1 headers, the driver actually upload s&r list
twice, in non-psp ucode front door loading phase and gfx pg initialization phase.
The latter is not allowed.
VG12 is the only exception where the driver still keeps legacy approach for S&R
list uploading. In theory, this can be elimnated if we have valid srcntl ucode
for VG12.
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Candice Li <Candice.Li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Set mmSQ_CONFIG.DISABLE_SMEM_SOFT_CLAUSE as W/R.
Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
PSP lost connection when err_event_athub occurs. These cleanup work can be
skipped in BACO reset.
v2: squash in missing include (Alex)
Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <hawking.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Fix gfx cgpg setting sequence for RLC deadlock at safe mode entry in polling gfx response.
The patch can fix VCN IB test failed and DAL get dispaly count failed issue.
Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Before disable gfx pipeline power gating need check the flag AMD_PG_SUPPORT_GFX_PIPELINE.
Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
v1: Add codes to query the EDC count of VML2 & ATCL2
v2: Rename VML2/ATCL2 registers and drop their mask define
v3: Add back the ECC mask for VML2 registers
Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Reviewed-by: Hawking Zhang <hawking.zhang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
For the potential request in the future, change to
query the actual EDC counter.
Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Reviewed-by: Hawking Zhang <hawking.zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
gfx_ras_late_init can get the info by itself
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
gfx_ras_fini can be shared among all generations of gfx
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
gfx ras ecc common functions could be reused among all gfx generations
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
change struct ras_err_data *err_data to void *err_data, align with
umc code and the callback's declaration in each ras block could
pay no attention to the structure type
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Never used.
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
For ASICs like renoir/arct, driver doesn't need to load mec2 jt.
when mec1 jt is loaded, mec2 jt will be loaded automatically
since the write is actaully broadcasted to both.
We need to more time to test other gfx9 asic. but for now we should
be able to draw conclusion that mec2 jt is not needed for renoir and
arct.
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
These is no LBPW on Renoir. So removing program of lbpw for renoir.
Signed-off-by: Aaron Liu <aaron.liu@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
add and_mask since the programming logic of golden setting changed
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Tianci.Yin <tianci.yin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
amdgpu_gfx_ras_late_init is used to init gfx specfic
ras debugfs/sysfs node and gfx specific interrupt handler.
It can be shared among gfx generations
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
to prevent access to dangling pointers
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Problem:
Under certain conditions, when some IP bocks take a RAS error,
we can get into a situation where a GPU reset is not possible
due to issues in RAS in SMU/PSP.
Temporary fix until proper solution in PSP/SMU is ready:
When uncorrectable error happens the DF will unconditionally
broadcast error event packets to all its clients/slave upon
receiving fatal error event and freeze all its outbound queues,
err_event_athub interrupt will be triggered.
In such case and we use this interrupt
to issue GPU reset. THe GPU reset code is modified for such case to avoid HW
reset, only stops schedulers, deatches all in progress and not yet scheduled
job's fences, set error code on them and signals.
Also reject any new incoming job submissions from user space.
All this is done to notify the applications of the problem.
v2:
Extract amdgpu_amdkfd_pre/post_reset from amdgpu_device_lock/unlock_adev
Move amdgpu_job_stop_all_jobs_on_sched to amdgpu_job.c
Remove print param from amdgpu_ras_query_error_count
v3:
Update based on prevoius bug fixing patch to properly call amdgpu_amdkfd_pre_reset
for other XGMI hive memebers.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|